Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Colombia Forestal
Print version ISSN 0120-0739
Abstract
TOVAR BLANCO, Adriana Lizeth; LIZARAZO SALCEDO, Iván Alberto and RODRIGUEZ ERASO, Nelly. Estimating aboveground biomass of Eucalyptus grandis and Pinus spp using Sentinel-1A and Sentinel-2A images in Colombia. Colomb. for. [online]. 2020, vol.23, n.1, pp.79-93. ISSN 0120-0739. https://doi.org/10.14483/2256201x.14854.
Aboveground biomass estimation, using machine-learning systems, is useful for rapid and systematic knowledge of productivity in forests and plantations. In this study, forest aboveground biomass (AGB) was estimated for plantations of Eucalyptus grandis and Pinus spp located in the central-eastern sector of the department of Cauca (Colombia), combining synthetic aperture radar (SAR) data of Sentinel-1A, Sentinel-2A optical data and forest inventory data and the use of the Random Forest algorithm. The variables with the highest incidence in AGB for E. grandis were the SWIR bands and the VV polarization textures, while for Pinus spp. were Correlationvv, GNDVI and B2. The models obtained by combining optical data and SAR show better results with a determination coefficient R2 = 0.27 and an average square error EMC = 42.75 t.ha-1 in E. grandis, and R2 = 0.36 and EMC = 141.71 t.ha-1 in Pinus spp. The study demonstrated the potential of combining Sentinel data to estimate AGB in commercial plantations and the use of Randon forest for model construction.
Keywords : GLCM; vegetation index; remote sensing; commercial forest plantation; Random Forest..